Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant actions or roles performed by subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Inherits
    -0.17
    ATUS
    -0.15
    ONSE
    -0.15
     MUST
    -0.15
    ouched
    -0.15
     Must
    -0.14
    izon
    -0.14
    ');?>"
    -0.14
    accumulate
    -0.14
     forControlEvents
    -0.14
    POSITIVE LOGITS
     starring
    0.32
     role
    0.30
     active
    0.29
     roles
    0.28
     leading
    0.27
     key
    0.27
     lead
    0.25
     central
    0.24
    leading
    0.24
    role
    0.24
    Act Density 0.026%

    No Known Activations